© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3700
    Prev
    Next
    INDEX
    Explanations

    resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    د
    0.81
     mercy
    0.75
     rage
    0.73
     causation
    0.72
     violation
    0.71
    persona
    0.70
    バッグ
    0.69
     extradition
    0.68
     steels
    0.67
     gentleman
    0.67
    POSITIVE LOGITS
     resources
    0.80
    $("#
    0.75
    $('#
    0.70
     immunos
    0.68
     beher
    0.67
    $('.
    0.67
    र्
    0.67
     untapped
    0.66
    RequestMethod
    0.66
    ר
    0.66
    Activations Density 0.046%

    No Known Activations